Compare/GPT-5.1 Codex mini (high) vs Qwen3.5 35B A3B (Reasoning)

GPT-5.1 Codex mini (high)vsQwen3.5 35B A3B (Reasoning)

Side-by-side comparison of pricing, 12 benchmarks, and generation speed.

OpenAI

GPT-5.1 Codex mini (high)

Input
$0.25/M
Output
$2/M
Speed
TTFT
Alibaba

Qwen3.5 35B A3B (Reasoning)

Input
$0.25/M
Output
$2/M
Speed
151 tok/s
TTFT
2.06s

Winner by Category

Cheaper
Tie
Faster (tok/s)
Qwen3.5 35B A3B (Reasoning)
Lower Latency
Qwen3.5 35B A3B (Reasoning)
Benchmarks (1-0)
GPT-5.1 Codex mini (high)

Pricing Comparison

MetricGPT-5.1 Codex mini (high)Qwen3.5 35B A3B (Reasoning)
Input ($/M tokens)$0.25$0.25
Output ($/M tokens)$2$2
Cost for 1M input + 100K output tokens:
GPT-5.1 Codex mini (high)$0.45
Qwen3.5 35B A3B (Reasoning)$0.45

Speed Comparison

Output Speed (tokens/s) — higher is better
GPT-5.1 Codex mini (high)
Qwen3.5 35B A3B (Reasoning)
151 tok/s
Time to First Token (seconds) — lower is better
GPT-5.1 Codex mini (high)
Qwen3.5 35B A3B (Reasoning)
2.06s

Editorial Analysis

Verdict. GPT-5.1 Codex mini (high) wins the overall benchmark matchup 1–0 across 1 overlapping categories, but raw benchmark score is only one input to the decision.

Pricing. Both models sit in the budget bracket for output-token pricing. At 1.0× the per-million-token cost, Qwen3.5 35B A3B (Reasoning) is meaningfully cheaper if your traffic is output-heavy (long completions, document generation, agent loops). Qwen3.5 35B A3B (Reasoning) makes more sense when output volume is low and absolute reasoning quality justifies the premium.

Strengths. GPT-5.1 Codex mini (high) is strongest on Intelligence Index (31.3). Qwen3.5 35B A3B (Reasoning) leads on Intelligence Index (29.9).

Speed. Speed data is incomplete for this pair; benchmark and price should decide.

Provider. OpenAI and Alibaba sell to overlapping but distinct developer audiences: OpenAI tends to ship frontier reasoning models with premium positioning, while Alibaba often prices more aggressively. Your existing vendor relationships, billing, and SLA preferences may matter as much as the raw numbers above.

Workload cost. Workload scenarios (per million requests at 30M input + 15M output tokens): GPT-5.1 Codex mini (high) costs $37.50 ($450/year); Qwen3.5 35B A3B (Reasoning) costs $37.50 ($450/year). At a smaller 5M-input/2M-output scale (single-developer tool or prototype): GPT-5.1 Codex mini (high) ≈ $5.25/run, Qwen3.5 35B A3B (Reasoning) ≈ $5.25/run. At agent/realtime scale (200M input / 100M output per million requests): GPT-5.1 Codex mini (high) ≈ $250/run, Qwen3.5 35B A3B (Reasoning) ≈ $250/run.

Recommendation. Both models have legitimate use cases — the right answer depends on whether you are optimizing for benchmark ceiling, latency, or unit cost. Start with the cheaper / faster model, evaluate against your specific task, and only switch if the upgrade shows a meaningful lift.

Head-to-head deltas

  • Aggregate benchmark score (sum across 12 categories, capped at 100): GPT-5.1 Codex mini (high) = 31, Qwen3.5 35B A3B (Reasoning) = 30. Within 15% — effectively equivalent if both meet the threshold your product requires.

Benchmark Comparison

Data from Artificial Analysis API — 12 benchmarks

Intelligence Index
31.329.9
Coding Index
Math Index
GPQA Diamond
MMLU-Pro
LiveCodeBench
AIME 2025
MATH-500
Humanity's Last Exam
SciCode
IFBench
TerminalBench
GPT-5.1 Codex mini (high)1 wins
0 winsQwen3.5 35B A3B (Reasoning)

Frequently Asked Questions

Which is cheaper, GPT-5.1 Codex mini (high) or Qwen3.5 35B A3B (Reasoning)?

Both models have similar pricing. Check the detailed breakdown above for input vs output token costs.

Which model performs better on benchmarks?

GPT-5.1 Codex mini (high) wins 1 out of 12 benchmarks compared to 0 for Qwen3.5 35B A3B (Reasoning). See the detailed benchmark chart above for per-category results.

Which is faster for real-time applications?

Qwen3.5 35B A3B (Reasoning) generates tokens faster at 151 tok/s vs — tok/s. However, Qwen3.5 35B A3B (Reasoning) has lower time-to-first-token (2.06s vs —s).

When should I use GPT-5.1 Codex mini (high) vs Qwen3.5 35B A3B (Reasoning)?

Choose based on your priorities: both are similarly priced, GPT-5.1 Codex mini (high) for stronger benchmark performance, and Qwen3.5 35B A3B (Reasoning) for faster generation. For latency-sensitive apps, check the TTFT comparison above.